"""
MalwareGuard — Independent 20k Benign URL Validation Suite.
Loads the retrained URL HyperModel ensemble and runs a massive diagnostic test
against the 20,000 completely unseen, nested benign URLs to verify dynamic robustness.
"""

import os
import sys
import time
import pandas as pd

# Configure python path to access backend services
workspace_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
backend_path = os.path.join(workspace_root, "backend")
sys.path.append(backend_path)

try:
    from app.services.url_service import URLModelService
    print("[OK] Successfully imported backend URLModelService.")
except ImportError as e:
    print(f"[ERROR] Failed to import backend services: {e}")
    sys.exit(1)

BENIGN_CSV = os.path.join(workspace_root, "data", "benign_20k_urls.csv")

def main():
    print("\n" + "="*70)
    print("  MASSIVE 20,000 UNSEEN BENIGN URLS DYNAMIC VALIDATION")
    print("="*70)

    if not os.path.exists(BENIGN_CSV):
        print(f"[ERROR] Benign dataset not found at {BENIGN_CSV}. Run generate_benign_validation.py first.")
        sys.exit(1)

    print(f"[INFO] Loading 20,000 benign URLs from {BENIGN_CSV}...")
    df = pd.read_csv(BENIGN_CSV)
    urls = df["url"].tolist()
    print(f"[INFO] Loaded {len(urls):,} URLs.")

    # Initialize URL model service pointing to local urlmodel_info
    models_dir = os.path.join(workspace_root, "urlmodel_info")
    print(f"[INFO] Initializing URL HyperModel from {models_dir}...")
    try:
        service = URLModelService(models_dir=models_dir)
    except Exception as e:
        print(f"[ERROR] Failed to initialize URL Model Service: {e}")
        sys.exit(1)

    print("\n[INFO] Running predictions... (This will take a few moments for 20k samples)")
    start_time = time.time()
    
    benign_count = 0
    malicious_count = 0
    
    # We will track samples that trigger false positives to print them as examples
    false_positives = []
    
    # Process in chunks with status prints
    total = len(urls)
    for idx, url in enumerate(urls):
        if idx > 0 and idx % 2000 == 0:
            print(f"  Processed {idx:,} / {total:,} URLs...")
            
        res = service.predict(url)
        verdict = res["prediction"]
        score = res["malicious_score"]
        
        if verdict == "Benign":
            benign_count += 1
        else:
            malicious_count += 1
            if len(false_positives) < 15:
                false_positives.append((url, score))
                
    elapsed = time.time() - start_time
    benign_acc = (benign_count / total) * 100
    fpr = (malicious_count / total) * 100
    avg_time = (elapsed / total) * 1000

    print("\n" + "="*60)
    print("  MASSIVE DYNAMIC VALIDATION RESULTS SUMMARY")
    print("="*60)
    print(f"  - Total Evaluated URLs : {total:,}")
    print(f"  - Classified as Benign  : {benign_count:,}")
    print(f"  - Classified as Malicious: {malicious_count:,} (False Positives)")
    print(f"  - Benign Accuracy        : {benign_acc:.3f}% (No False Positives)")
    print(f"  - False Positive Rate    : {fpr:.3f}%")
    print(f"  - Total Elapsed Time     : {elapsed:.2f} seconds")
    print(f"  - Average Inference Time : {avg_time:.2f} ms / URL")
    print("-"*60)

    if false_positives:
        print("\n[INFO] First 15 False Positive Examples (ordered by score):")
        # Sort false positives by score descending
        false_positives.sort(key=lambda x: x[1], reverse=True)
        for url, score in false_positives:
            print(f"  - Score: {score:.5f} | URL: {url}")
    else:
        print("\n[SUCCESS] PERFECT 0.0% FALSE POSITIVE RATE ACHIEVED!")

    print("="*60)
    
    # Standard acceptable FPR for security platforms is < 2.0%
    if fpr <= 2.0:
        print("  DEDICATED QUALITY ASSURANCE: PASSED!")
        print("  The model shows exceptional dynamic path generalization.")
        print("="*60)
        sys.exit(0)
    else:
        print("  DEDICATED QUALITY ASSURANCE: FAILED (FPR > 2.0%).")
        print("  Further dataset adjustments needed.")
        print("="*60)
        sys.exit(1)

if __name__ == "__main__":
    main()